• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.4
• /
• pp.488-493
• /
• 2007

In general, recommendation systems quantify real-time context information obtained in the stage of collaborative filtering and use quantified context information in order to recommend services. But the recommendation systems can have problems of recommending inaccurate information because of lack of context information or classifying users into inaccurate groups because of simple classification works in the stage of quantification. In this paper, we solved the problems of lack of context information obtained in real-time by combining users' profile information used in the contents-based filtering and context information obtained in real-time. In addition, we tried collaborative filtering at the quantification stage by improving absolute classification methods to relative ones. As the result of experiments, this method improved prediction preference by 5.8% than real-time recommendation systems using context information in pure P2P environment.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1111-1120
• /
• 2005

In collaborative filtering systems most users do not rate preferences; so User-Item matrix shows great sparsity because it has missing values for items not rated by users. Generally, the systems predict the preferences of an active user based on the preferences of a group of users. However, default voting methods predict all missing values for all users in User-Item matrix. One of the most common methods predicting default voting values tried two different approaches using the average rating for a user or using the average rating for an item. However, there is a problem that they did not consider the characteristics of items, users, and the distribution of data set. We replace the missing values in the User-Item matrix by the default noting method using user coefficient of variance. We select the threshold of user coefficient of variance by using equations automatically and determine when to shift between the user averages and item averages according to the threshold. However, there are not always regular relations between the averages and the thresholds of user coefficient of variances in datasets. It is caused that the distribution information of user coefficient of variances in datasets affects the threshold of user coefficient of variance as well as their average. We decide the threshold of user coefficient of valiance by combining them. We evaluate our method on MovieLens dataset of user ratings for movies and show that it outperforms previously default voting methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.183-188
• /
• 2021

Collaborative filtering based recommender systems are currently indispensable function of commercial systems in various fields, being a useful service by providing customized products that users will prefer. However, there is a high possibility that the prediction of preferrable products is inaccurate, when the user's rating data are insufficient. In order to overcome this drawback, this study suggests a stepwise method for prediction of product ratings. If the application conditions of the prediction method corresponding to each step are not satisfied, the method of the next step is applied. To evaluate the performance of the proposed method, experiments using a public dataset are conducted. As a result, our method significantly improves prediction and precision performance of collaborative filtering systems employing various conventional similarity measures and outperforms performance of the previous methods for solving rating data sparsity.

• Journal of Information Technology Applications and Management
• /
• v.30 no.4
• /
• pp.29-38
• /
• 2023

A single-learner model which integrates the user's positive and negative perceptions is proposed by augmenting counterfactual data to the interaction data between users and items, which are mainly used in collaborative filtering in this study. The proposed CausRec showed superior performance compared to the existing NCF model in terms of F1 value and AUC in experiments using three published datasets: MovieLens 100K, Amazon Gift Card, and Amazon Magazine. Compared to the existing NCF model, the F1 and AUC values of CausRec showed 1.2% and 2.6% performance improvement in MovieLens 100K data, and 2.2% and 10% improvement in Amazon Gift Card data, respectively. In particular, in experiments using Amazon Magazine data, F1 and AUC values were improved by 11.7% and 21.9%, respectively, showing a significant performance improvement effect. The performance of CausRec is improved because both positive and negative perceptions of the item were reflected in the recommendation at the same time. It is judged that the proposed method was able to improve the performance of the collaborative filtering because it can simultaneously alleviate the sparsity and imbalance problems of the interaction data.

• Journal of The Korean Association of Information Education
• /
• v.17 no.4
• /
• pp.375-382
• /
• 2013

Collaborative filtering has been most widely used in commercial sites to recommend items based on the history of user preferences for items. The basic idea behind this method is to find similar users whose ratings for items are incorporated to make recommendations for new items. Hence, similarity calculation is most critical in recommendation performance. This paper presents a new similarity measure that takes each rating of a user relatively to his own ratings. Extensive experiments revealed that the proposed measure is more reliable than the classic measures in that it significantly decreases generation of extreme similarity values and its performance improves when consulting neighbors with high similarites only. In particular, the results show that the proposed measure is superior to the classic ones for datasets with large rating scales.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.203-210
• /
• 2020

Memory-based collaborative filtering is one of the representative types of the recommender system, but it suffers from the inherent problem of data sparsity. Although many works have been devoted to solving this problem, there is still a request for more systematic approaches to the problem. This study exploits distribution of user ratings given to items for computing similarity. All user ratings are utilized in the proposed method, compared to previous ones which use ratings for only common items between users. Moreover, for similarity computation, it takes a global view of ratings for items by reflecting other users' ratings for that item. Performance is evaluated through experiments and compared to that of other relevant methods. The results reveal that the proposed demonstrates superior performance in prediction and rank accuracies. This improvement in prediction accuracy is as high as 2.6 times more than that achieved by the state-of-the-art method over the traditional similarity measures.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.357-359
• /
• 2023

This paper proposes a hybrid recommendation system (RS) model that overcomes the limitations of traditional approaches such as data sparsity, cold start, and scalability by combining collaborative filtering and context-aware techniques. The objective of this model is to enhance the accuracy of recommendations and provide personalized suggestions by leveraging the strengths of collaborative filtering and incorporating user context features to capture their preferences and behavior more effectively. The approach utilizes a novel method that combines contextual attributes with the original user-item rating matrix of CF-based algorithms. Furthermore, we integrate k-mean++ clustering to group users with similar preferences and finally recommend items that have highly rated by other users in the same cluster. The process of partitioning is the use of the rating matrix into clusters based on contextual information offers several advantages. First, it bypasses of the computations over the entire data, reducing runtime and improving scalability. Second, the partitioned clusters hold similar ratings, which can produce greater impacts on each other, leading to more accurate recommendations and providing flexibility in the clustering process. keywords: Context-aware Recommendation, Collaborative Filtering, Kmean++ Clustering.

• Journal of Internet Computing and Services
• /
• v.23 no.1
• /
• pp.125-134
• /
• 2022

The development of information communication and artificial intelligence technology requires the intelligent command and control (C2) system for Korean military, and various studies are attempted to achieve it. In particular, as a volume ofinformation in the C2 workflow increases exponentially, this study pays attention to the collaborative filtering (CF) and recommendation systems (RS) that can provide the essential information for the users of the C2 system has been developed. The RS performing information filtering in the C2 system should provide an explanatory recommendation and consider the context of the tasks and users. In this paper, we propose a contextual pre-filtering CARS framework that recommends information in the C2 workflow. The proposed framework consists of four components: 1) contextual pre-filtering that filters data in advance based on the context and relationship of the users, 2) feature selection to overcome the data sparseness that is a weak point for the CF, 3) the proposed CF with the features distances between the users used to calculate user similarity, and 4) rule-based post filtering to reflect user preferences. In order to evaluate the superiority of this study, various distance methods of the existing CF method were compared to the proposed framework with two experimental datasets in real-world. As a result of comparative experiments, it was shown that the proposed framework was superior in terms of MAE, MSE, and MSLE.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.2
• /
• pp.379-386
• /
• 2014

As the use of mobile device is increasing rapidly, the number of users is also increasing. However, most of the app stores are using recommendation of simple ranking method, so the accuracy of recommendation is lower. To recommend an item that is more appropriate to the user, this paper proposes a technique that reflects the weight of user information and recent preference degree of item. The proposed technique classifies the data set by categories and then derives a predicted value by applying the user's information weight to the collaborative filtering technique. To reflect the recent preference degree of item by categories, the average of items' rating values in the designated period is computed. An item is recommended by combining the two result values. The experiment result indicated that the proposed method has been more enhanced the accuracy, appropriacy, compared to item-based, user-based method.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.219-239
• /
• 2019

As the importance of providing customized services to individuals becomes important, researches on personalized recommendation systems are constantly being carried out. Collaborative filtering is one of the most popular systems in academia and industry. However, there exists limitation in a sense that recommendations were mostly based on quantitative information such as users' ratings, which made the accuracy be lowered. To solve these problems, many studies have been actively attempted to improve the performance of the recommendation system by using other information besides the quantitative information. Good examples are the usages of the sentiment analysis on customer review text data. Nevertheless, the existing research has not directly combined the results of the sentiment analysis and quantitative rating scores in the recommendation system. Therefore, this study aims to reflect the sentiments shown in the reviews into the rating scores. In other words, we propose a new algorithm that can directly convert the user 's own review into the empirically quantitative information and reflect it directly to the recommendation system. To do this, we needed to quantify users' reviews, which were originally qualitative information. In this study, sentiment score was calculated through sentiment analysis technique of text mining. The data was targeted for movie review. Based on the data, a domain specific sentiment dictionary is constructed for the movie reviews. Regression analysis was used as a method to construct sentiment dictionary. Each positive / negative dictionary was constructed using Lasso regression, Ridge regression, and ElasticNet methods. Based on this constructed sentiment dictionary, the accuracy was verified through confusion matrix. The accuracy of the Lasso based dictionary was 70%, the accuracy of the Ridge based dictionary was 79%, and that of the ElasticNet (${\alpha}=0.3$) was 83%. Therefore, in this study, the sentiment score of the review is calculated based on the dictionary of the ElasticNet method. It was combined with a rating to create a new rating. In this paper, we show that the collaborative filtering that reflects sentiment scores of user review is superior to the traditional method that only considers the existing rating. In order to show that the proposed algorithm is based on memory-based user collaboration filtering, item-based collaborative filtering and model based matrix factorization SVD, and SVD ++. Based on the above algorithm, the mean absolute error (MAE) and the root mean square error (RMSE) are calculated to evaluate the recommendation system with a score that combines sentiment scores with a system that only considers scores. When the evaluation index was MAE, it was improved by 0.059 for UBCF, 0.0862 for IBCF, 0.1012 for SVD and 0.188 for SVD ++. When the evaluation index is RMSE, UBCF is 0.0431, IBCF is 0.0882, SVD is 0.1103, and SVD ++ is 0.1756. As a result, it can be seen that the prediction performance of the evaluation point reflecting the sentiment score proposed in this paper is superior to that of the conventional evaluation method. In other words, in this paper, it is confirmed that the collaborative filtering that reflects the sentiment score of the user review shows superior accuracy as compared with the conventional type of collaborative filtering that only considers the quantitative score. We then attempted paired t-test validation to ensure that the proposed model was a better approach and concluded that the proposed model is better. In this study, to overcome limitations of previous researches that judge user's sentiment only by quantitative rating score, the review was numerically calculated and a user's opinion was more refined and considered into the recommendation system to improve the accuracy. The findings of this study have managerial implications to recommendation system developers who need to consider both quantitative information and qualitative information it is expect. The way of constructing the combined system in this paper might be directly used by the developers.